On Using the Exact Sampling Distribution of Multivariate Coefficient of Variation

Authors

  • David Sam Jayakumar Jamal Institute of Management, Jamal Mohamed College, Bharathidasan University, Trichy, Tamil Nadu, India
  • Sulthan Ayyup Kan Jamal Institute of Management, Jamal Mohamed College, Bharathidasan University, Trichy, Tamil Nadu, India
  • Samuel Wilfred Jamal Institute of Management, Jamal Mohamed College, Bharathidasan University, Trichy, Tamil Nadu, India

Keywords:

Sample multivariate coefficient of variation, normal population, non-central F-ratio, confluent hyper-geometric function, biased estimator

Abstract

The objective of this manuscript is to propose the exact sampling distribution of sample multivariate coefficient of variation from the normal population. The authors identified its relationship between sample mcv and non-central F-ratio and derived the density function in terms of confluent hyper geometric function by using Jacobian method of one dimensional transformation kth order moment and they proved the p-variate sample (cv)p is the biased estimator of the true or population (cv)p Moreover, the shape of the density function of sample multivariate coefficient of variation is also visualized and the authors computed the critical points of sample  (cv)at 5% and 1% significance level for different sample sizes. Using the Iris plants database in the pattern recognition literature and has shown a numerical study for testing the significance of the sample uni-variate, bi-variate, tri-variate and multivariate coefficient of variation.

Downloads

Download data is not yet available.

Downloads

Published

2021-06-29

Issue

Section

Articles